Solving Prompt Injection via Backtranslation (arxiv.org) | HN Screenshots

YHacker Newsscreenshots

Screenshot of arxiv.org: Solving Prompt Injection via Backtranslation

First screen, captured 2 years ago.

Looks similar

Screenshot of arxiv.org: ArtPrompt: ASCII Art-Based Jailbreak Attacks Against Aligned LLMs

ArtPrompt: ASCII Art-Based Jailbreak Attacks Against Aligned LLMs (arxiv.org)

125 points by wut42 2 years ago | 35 comments

Screenshot of arxiv.org: SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks

SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks (arxiv.org)

42 points by amai 1 year ago | 15 comments

Screenshot of arxiv.org: LLM agents can autonomously hack websites

LLM agents can autonomously hack websites (arxiv.org)

56 points by pella 2 years ago | 16 comments

Screenshot of arxiv.org: TransTroj: Transferable Backdoor Attacks to Pre-Trained Models

TransTroj: Transferable Backdoor Attacks to Pre-Trained Models (arxiv.org)

10 points by indus 2 years ago | 0 comments

Screenshot of arxiv.org: InternLM2

InternLM2 (arxiv.org)

121 points by milliondreams 2 years ago | 21 comments

Screenshot of arxiv.org: Scalable MatMul-Free Language Modeling

Scalable MatMul-Free Language Modeling (arxiv.org)

177 points by lykahb 2 years ago | 27 comments